8 papers
Words to World: Benchmarking LLMs in Interactive Physical Environments
Xinnan Dai, Kaiqi Yang, Yaxin Li +9
Words are increasingly becoming an interface for action: large language models (LLMs) can now invoke tools, operate devices, and make decisions that affect the physical world. Howe…
AREX: Towards a Recursively Self-Improving Agent for Deep Research
Shuqi Lu, Chaofan Li, Kun Luo +21
Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candidate can often be decomposed i…
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
Wanli Li, Bowen Zhou, Yunyao Yu +4
Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and external tools. Existing benchm…
LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent
Bince Qu, Wanli Li, Bo Pan +5
Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents. However, scaling agentic RL for deep research remains constrained by two coupled chall…
ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents
Bowen Zhou, Zhou Xu, Wanli Li +3
Training-free KV cache compression is essential for deploying vision-language GUI agents under memory and latency constraints, yet existing methods are designed for generic languag…
SAIL: Self-Amplified Iterative Learning for Diffusion Model Alignment with Minimal Human Feedback
Xiaoxuan He, Siming Fu, Wanli Li +5
Aligning diffusion models with human preferences remains challenging, particularly when reward models are unavailable or impractical to obtain, and collecting large-scale preferenc…
TempFlow-GRPO: When Timing Matters for GRPO in Flow Models
Xiaoxuan He, Siming Fu, Yuke Zhao +5
Recent flow matching models for text-to-image generation have achieved remarkable quality, yet their integration with reinforcement learning for human preference alignment remains…
OmniGen2: Towards Instruction-Aligned Multimodal Generation
Chenyuan Wu, Pengfei Zheng, Ruiran Yan +19
In this work, we introduce OmniGen2, a versatile and open-source generative model designed to provide a unified solution for diverse generation tasks, including text-to-image, imag…